Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models

• URL: http://arxiv.org/abs/2511.07498v1
• Date: Wed, 12 Nov 2025 01:01:43 GMT
• Title: Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models
• Authors: Xin Liu, Qiyang Song, Qihang Zhou, Haichao Du, Shaowen Xu, Wenbo Jiang, Weijuan Zhang, Xiaoqi Jia,
• Abstract summary: We study the contribution of multi-head self-attention in supporting multilingual processing in large language models (LLMs)<n>Applying LAHIS to Aya-23-8B, Llama-3.2-3B, and Mistral-7B-v0.1, we reveal the existence of both language-specific and language-general heads.<n>We also introduce a lightweight adaptation that learns a soft head mask to modulate attention outputs over language heads, requiring only 20 tunable parameters to improve XQuAD accuracy.
• Score: 8.746854869825318
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) increasingly support multilingual understanding and generation. Meanwhile, efforts to interpret their internal mechanisms have emerged, offering insights to enhance multilingual performance. While multi-head self-attention (MHA) has proven critical in many areas, its role in multilingual capabilities remains underexplored. In this work, we study the contribution of MHA in supporting multilingual processing in LLMs. We propose Language Attention Head Importance Scores (LAHIS), an effective and efficient method that identifies attention head importance for multilingual capabilities via a single forward and backward pass through the LLM. Applying LAHIS to Aya-23-8B, Llama-3.2-3B, and Mistral-7B-v0.1, we reveal the existence of both language-specific and language-general heads. Language-specific heads enable cross-lingual attention transfer to guide the model toward target language contexts and mitigate off-target language generation issue, contributing to addressing challenges in multilingual LLMs. We also introduce a lightweight adaptation that learns a soft head mask to modulate attention outputs over language heads, requiring only 20 tunable parameters to improve XQuAD accuracy. Overall, our work enhances both the interpretability and multilingual capabilities of LLMs from the perspective of MHA.

Related papers

• Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models [60.39744129890118]
  Large vision-language models (LVLMs) have demonstrated exceptional capabilities in understanding visual information with human languages.<n>In this work, we identify a salient correlation between the multilingual understanding ability of LVLMs and language-specific neuron activations in shallow layers.<n>We introduce PLAST, a training recipe that achieves efficient multilingual enhancement for LVLMs by Precise LAnguage-Specific layers fine-Tuning.
  arXiv  Detail & Related papers  (2025-08-25T18:15:25Z)
• CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention [56.08815340137881]
  Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal abilities but remain prone to multilingual object hallucination.<n>We propose Cross-Lingual Attention Intervention for Mitigating multilingual object hallucination (CLAIM) in LVLMs, a novel near training-free method by aligning attention patterns.
  arXiv  Detail & Related papers  (2025-06-03T11:17:16Z)
• Lens: Rethinking Multilingual Enhancement for Large Language Models [70.85065197789639]
  We propose Lens, a novel approach to enhance multilingual capabilities in large language models (LLMs)<n>Lens operates on two subspaces: the language-agnostic subspace, where it aligns target languages with the central language to inherit strong semantic representations, and the language-specific subspace, where it separates target and central languages to preserve linguistic specificity.<n>Lens significantly improves multilingual performance while maintaining the model's English proficiency, achieving better results with less computational cost compared to existing post-training approaches.
  arXiv  Detail & Related papers  (2024-10-06T08:51:30Z)
• 1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators? [46.43162333819418]
  Large Language Models (LLMs) have garnered significant attention due to their remarkable ability to process information across various languages. Despite their capabilities, they exhibit inconsistencies in handling identical queries in different languages, presenting challenges for further advancement. This paper introduces a method to enhance the multilingual performance of LLMs by aggregating knowledge from diverse languages.
  arXiv  Detail & Related papers  (2024-06-20T20:32:53Z)
• A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers [51.8203871494146]
  The rapid development of Large Language Models (LLMs) demonstrates remarkable multilingual capabilities in natural language processing.<n>Despite the breakthroughs of LLMs, the investigation into the multilingual scenario remains insufficient.<n>This survey aims to help the research community address multilingual problems and provide a comprehensive understanding of the core concepts, key techniques, and latest developments in multilingual natural language processing based on LLMs.
  arXiv  Detail & Related papers  (2024-05-17T17:47:39Z)
• Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models [79.46179534911019]
  Large language models (LLMs) have demonstrated multilingual capabilities, yet they are mostly English-centric due to imbalanced training corpora.<n>We extend the evaluation to real-world user queries and non-English-centric LLMs, offering a broader examination of multilingual performance.
  arXiv  Detail & Related papers  (2024-03-15T12:47:39Z)
• How do Large Language Models Handle Multilingualism? [81.15060972112563]
  This study explores how large language models (LLMs) handle multilingualism. LLMs initially understand the query, converting multilingual inputs into English for task-solving. In the intermediate layers, they employ English for thinking and incorporate multilingual knowledge with self-attention and feed-forward structures.
  arXiv  Detail & Related papers  (2024-02-29T02:55:26Z)
• Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models [117.20416338476856]
  Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. We propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons.
  arXiv  Detail & Related papers  (2024-02-26T09:36:05Z)
• How Vocabulary Sharing Facilitates Multilingualism in LLaMA? [19.136382859468693]
  Large Language Models (LLMs) often show strong performance on English tasks, while exhibiting limitations on other languages. This study endeavors to examine the multilingual capability of LLMs from the vocabulary sharing perspective.
  arXiv  Detail & Related papers  (2023-11-15T16:13:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.